2 citations · 3 across the 9 of their papers we have counts for
10 papers
Relational Compression: A Framework for Relational Fidelity in Constrained Representations
Yaniv Shulman
What should a compressed representation preserve when the information of interest lies in relationships among elements rather than in the elements themselves? We formulate relation…
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
Yaniv Shulman, Shaghayegh Akbarpour, Jack B. Muir
We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from…
Generalized Local Polynomial Regression with Decomposed Context-Aware Kernels
Yaniv Shulman
Local Polynomial Regression (LPR) is a powerful tool for nonparametric smoothing, yet it traditionally suffers from a "Euclidean tautology": the variables used to define the local…
Bayesian Modeling and Estimation of Linear Time-Varying Systems using Neural Networks and Gaussian Processes
Yaniv Shulman
The identification of Linear Time-Varying (LTV) systems from input-output data is a fundamental yet challenging ill-posed inverse problem. This work introduces a unified Bayesian f…
Robust Local Polynomial Regression with Similarity Kernels
Yaniv Shulman
Local Polynomial Regression (LPR) is a widely used nonparametric method for modeling complex relationships due to its flexibility and simplicity. It estimates a regression function…
Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations
Yaniv Shulman
Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision…
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and Regularization
Yaniv Shulman
Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness which demonstrates they are…
SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
Yaniv Shulman
Deep learning methods for graphs have seen rapid progress in recent years with much focus awarded to generalising Convolutional Neural Networks (CNN) to graph data. CNNs are typica…
Dynamic Time Warp Convolutional Networks
Yaniv Shulman
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant al…
Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
Yaniv Shulman
A method for unsupervised contextual anomaly detection is proposed using a cross-linked pair of Variational Auto-Encoders for assigning a normality score to an observation. The met…